Professional Documents
Culture Documents
Residual Compensation-Based Extreme Learning Machine For MIMO-NOMA Receiver
Residual Compensation-Based Extreme Learning Machine For MIMO-NOMA Receiver
This is the author's version which has not been fully edited and
content may change prior to final publication. Citation information: DOI 10.1109/ACCESS.2023.3242917
Date of publication xxxx 00, 0000, date of current version xxxx 00, 0000.
Digital Object Identifier xx.xxxx/ACCESS.xxxx.DOI
ABSTRACT
Extreme learning machine (ELM) uses a simple machine learning (ML) architecture that allows its
implementation for smart IoT network operations. However, some inaccuracy lies between the predicted and
the actual data during the ELM training, which can be caused due to the limitation of the modeling repre-
sentation. This paper thus investigates a residual compensation-based ELM (RC-ELM) for its application in
designing a receiver for MIMO-NOMA aided IoT systems. In RC-ELM, the base ELM layers determine the
relationship between the transmitted and received data and the additional layers of the RC-ELM attempt to
compensate the error introduced during the training mechanism. The analysis of the appropriate number of
compensation layers for training error minimization is conducted on the basis of the bit error rate (BER) and
the error vector magnitude (EVM) performances of the RC-ELM training. A minimum BER improvement
of 5% for user 1 and 18% for user 2 is shown with with the aid of RC-ELM for a two-IoT user instance.
The EVM is marginally increased by 0.0008% for user 1 and 1.61% for user 2 in training stage. Besides,
the RC-ELM receiver is also compared to the minimum mean square error (MMSE), the classic ELM and
the trained multilayer perceptron (MLP) receivers in terms of BER and EVM. Both of the ELM receivers
show improved performances with respect to the other receivers.
INDEX TERMS IoT, MIMO-NOMA, machine learning, extreme learning machine, RC-ELM, multilayer
perceptron.
VOLUME 4, 2016 1
This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://creativecommons.org/licenses/by/4.0/
This article has been accepted for publication in IEEE Access. This is the author's version which has not been fully edited and
content may change prior to final publication. Citation information: DOI 10.1109/ACCESS.2023.3242917
allocations are accommodated in same time and frequency based receiver systems are proposed which do not require
resources. Later, the signals from multiple sources are super- any channel information. However, due to the limitation
imposed and transmitted to the desired destination. However, of modeling representation, some training inaccuracy may
this leads to the inter-user interference problem since the be introduced during the learning stage as ML approaches,
time and frequency resources utilized by the users are non- including ELM, might not always reach the global minima
orthogonal, and consequently complicates the extraction of with the given ML parameters. Thus regularization tech-
the required information from the received signal. Thus, nique is applied to ensure that the ML algorithms perform
several studies are being conducted on MIMO-NOMA signal well when generalized. A residual compensation-based ELM
processing, which includes channel estimation, signal detec- (RC-ELM) is proposed for building the MIMO-NOMA re-
tion and interference cancellation operations. In [2], a zero- ceiver in order to reduce training error. To our knowledge,
forcing (ZF) beamforming is studied for multi-user down- this is the first time an RC-ELM has been researched in
link MIMO-NOMA system where each cluster contains two relation to creating a MIMO-NOMA receiver. The following
single-antenna user devices. Channel state information (CSI) highlights the paper’s contribution.
of each cluster-head is extracted for the ZF beamforming • An RC-ELM-based receiver is presented for a multi-
design. Maximum-likelihood based receiver is utilized in [3] user MIMO-NOMA aided IoT system. The base ELM
for uplink MIMO-NOMA to detect quadrature phase shift layers are used to map the transmitted and received data,
keying (QPSK) modulated symbols. A precoding scheme, whereas the additional layers are used to compensate
which focuses on minimization of transmission power con- the error introduced during training. A bit error rate
sumption, is suggested in [4] where the transmitted signal is (BER) analysis of choosing the effective number of
recovered with the help of the precoder and the minimum compensation layers to mitigate training error by means
mean square error (MMSE) equalizer. An iterative linear of the RC-ELM receiver is conducted.
MMSE (LMMSE) is designed in [5] multiuser detection • The performance of the proposed ELM receiver is con-
in MIMO-NOMA system. The mismatch between LMMSE trasted with that of the MMSE, multilayer perceptron
detection and decoding is attempted to remove in the study (MLP) and classic ELM receivers. It is demonstrated
for better signal recovery and achievable rate is then an- that both of the ELM receivers provides better BER than
alyzed. The performance of these approaches depends on the MMSE and the MLP receivers.
the accuracy of the channel estimation. Besides, the inter-
user interference mitigation approaches required in MIMO- The paper is organized as follows. Section II discusses
NOMA also relies on channel information-based techniques the MIMO-NOMA system model, which includes data trans-
[6]. However, parameters such as auto-covariance of the mission and reception, channel estimation and signal detec-
channel and noise variance are challenging to obtain in tion with linear receiver. Section III discusses the basics of
practical communication systems [7]. One possible approach ELM-based receiver and section IV discusses the RC-ELM
can be the adoption of machine learning (ML) techniques to receiver. Section V presents the simulation parameters and
conduct such signal processing mechanisms [8]. discussions on the results. Section VI concludes the paper.
Several studies on ML algorithm such as deep neural Notations: Matrix is represented by the bold uppercase let-
network (DNN)-based approaches are conducted for MIMO- ters, vector is represented by bold lowercase letters and scalar
NOMA systems to detect signals [9]–[11]. DNN based pre- variables are represented by small letters. The inverse, trans-
coding and decoding approaches are proposed in [9] for pose, conjugate transpose and Moore-Penrose inverse oper-
MIMO-NOMA system with successive interference cancel- ations are denoted by (.)−1 , (.)T , (.)∗ and (.)† respectively.
lation (SIC) scheme. Uplink signal detection for MIMO- The matrix inverse operation with regularization parameter
´ Activation function is represented by
is represented by (.).
NOMA is performed by means of convolutional neural net-
works (CNN) in [10]. The iterative soft-thresholding tech- G(.). The Frobenius norm of a matrix is denoted by ||.||F .
nique is the foundation of the adaptive DL-based receiver
architecture known as MMNet [11]. The performance of the II. SYSTEM MODEL
MMNet receiver is evaluated for massive MIMO (mMIMO) A. MIMO-NOMA DATA TRANSMISSION AND RECEPTION
channel with spatial correlation. However, the tuning of DNN A visual representation of the downlink MIMO-NOMA sys-
parameters such as weights and biases are performed by tem is presented in Fig. 1. The source data bits for the IoT
means of iterative mechanisms, which may complicate the user k are digitally modulated. Afterwards, inverse discrete
implementation of such DNN algorithms. Contrary to the Fourier transformation (IDFT) of the data symbols of each
tuning mechanism-based ML algorithms, extreme learning IoT user is carried out, followed by cyclic prefix (CP) ad-
machine (ELM) uses randomly assigned input weights and dition. Each user is allocated with power pk and multiplied
biases (that connect between the input layer and the hidden with the respective signals. Later, the respective signals are
layer) and perform supervised learning with the help of train- added. After that, the superposed data transferred to the
ing datasets by determining the output weights (connecting receiver through wireless channel [14]. After receiving the
the hidden layer and the output layer), which is responsible superposed data by each IoT user, CP is removed and discrete
for determining the desired output. In [12], [13], the ELM- Fourier transformation (DFT) is carried out. The received
2 VOLUME 4, 2016
This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://creativecommons.org/licenses/by/4.0/
This article has been accepted for publication in IEEE Access. This is the author's version which has not been fully edited and
content may change prior to final publication. Citation information: DOI 10.1109/ACCESS.2023.3242917
This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://creativecommons.org/licenses/by/4.0/
This article has been accepted for publication in IEEE Access. This is the author's version which has not been fully edited and
content may change prior to final publication. Citation information: DOI 10.1109/ACCESS.2023.3242917
This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://creativecommons.org/licenses/by/4.0/
This article has been accepted for publication in IEEE Access. This is the author's version which has not been fully edited and
content may change prior to final publication. Citation information: DOI 10.1109/ACCESS.2023.3242917
Input: Y γ,k , X γ
Random assignment of the input weight W k and the bias
bk
Computation of the hidden layer neuron parameter M γk
from (6)
Determination of output weight β 0,k from (7)
Computation of Ê γ,s from (15) and τs from (17) for sth
compensation layer1
TESTING OF ELM
Input: Y k , τs , and Ê γ,s
Computation of hidden layer neuron parameter M from FIGURE 4. BER vs. SNR for the classic ELM receiver as a function of
different hidden layer neurons.
(8)
Determination of X̂ k,ELM from (9)
Determination of X̂ k,RC−ELM from (18) V. SIMULATION RESULTS
The first compensation layer operation will always be performed according This section presents the simulation results for MIMO-
to (11)-(12). NOMA communication system operating at 30 GHz carrier
frequency. The user 1 and user 2 are respectively at the
distances 20 m and 10 m apart from the BS. The transmission
Here, τs represents the weights
PS of each compensation layer power is considered to be 30 dBm and the values of p1
which fulfills the criteria s=1 τs = 1. The compensation and p2 for user 1 and user 2 are respectively 0.92 and
layer weights can be calculated as follows. 0.08. Normalized 16-quadrature amplitude modulation (16-
1
QAM) is chosen in our study. Transmitted data are organized
||E γ,s −Ê γ,s ||F in physical resource block (PRB) arrangement [12]. The
τs = (17)
PS 1 transmitted and received reference symbols at one OFDM
s=1 ||E γ,s −Ê γ,s ||F
symbol time are considered for channel estimation as well as
In the testing stage, the estimated errors and the compen- the online training of both of the ELM receivers and the MLP
sation layer weights are used. After performing equalization receiver. The parameters of simulation are stated in Table 1.
according to (9), the final output by means of RC-ELM for To design both the ELM receivers, activation function tanh
the IoT user k can be represented as follows. is used [12], [13]. The input weights W and biases b follow
uniform distribution within the interval [-0.01,0.01]. The
S input layer in both the ELM receivers consists of 2 neurons
(each neuron takes the symbols received at each antenna)
X
X̂ k,RC−ELM = X̂ k,ELM + τs Ê γ,s (18)
s=1 and the output layer consists of 4 neurons (each neuron
takes the symbols transmitted from each antenna). Fig. 4
The mechanism of the RC-ELM receiver is summarized in demonstrates the BER obtained by adopting the classic ELM-
Algorithm 1. based receiver with different hidden layer neurons, which are
L1 = 2, L2 = 4 and L3 = 8. It is observed that the BER for
L2 and L3 is superior to that for L1 . Besides, the difference
in BER values for L2 and L3 is almost negligible in all SNR
TABLE 1. Simulation parameters. values. For simplicity, L2 = 4 is chosen in this study for both
of the classic ELM and the RC-ELM receivers.
Parameters Value/Technique
MIMO configuration NR × Nt 2×4 Fig. 5 demonstrates the BER obtained by the classic ELM
Number of IoT users, K 2 receiver and the RC-ELM receiver in training stage with 2, 3
Number of BS 1 and 4 compensation layers. As the regularization parameter
Modulation format 16QAM
Transmission power 30 dBm α varies from 10−2 to 10−5 , the BER performance improves
SNR (dB) 0-50 with the increase of SNR. The RC-ELM receiver is able
Number of PRB 66 to provide lower BER than the classic ELM. The RC-ELM
Number of subcarrier per PRB 12
Carrier frequency 30 GHz with 2 compensation layers shows lower BER with respect
Subcarrier spacing 120 kHz to the RC-ELM with 3 and 4 compensation layers. In Fig.
Number of OFDM symbols per slot 14 5d, the BER values of the classic ELM receiver is very
VOLUME 4, 2016 5
This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://creativecommons.org/licenses/by/4.0/
This article has been accepted for publication in IEEE Access. This is the author's version which has not been fully edited and
content may change prior to final publication. Citation information: DOI 10.1109/ACCESS.2023.3242917
(a) (b)
(c) (d)
−2 −3
FIGURE 5. BER for ELM and RC-ELM-based MIMO-NOMA receivers in training stage with (a) α = 10 (b) α = 10 (c) α = 10−4 (d) α = 10−5 .
similar to that of the RC-based receiver, although marginal 4.7%, 0.34%, 0.01% and 0.0008% respectively. For user 2,
improvement is observed in high SNR values. For instance, the EVM performance, for α = 102 , 103 , 104 and 105 , is
at SNR=35 dB, compared to the classic ELM receiver, the improved by 9.2%, 13.5%, 0.28% and 1.61% within the same
RC-ELM provides about 5% lower BER for user 1 and SNR values. Based on the BER and the EVM performances
about 18% lower BER for user 2. Table 2 presents the observed with the reference symbols, the number of compen-
EVM performance (determined on the basis of the Euclidean sation layers in RC-ELM in testing stage is chosen to be 2.
distance between the equalized symbols and the reference An MLP-based receiver is also implemented in this study
constellation symbols) of the classic ELM and the RC-ELM for performance comparison [20]. A three hidden layer
receivers with training symbols. Overall, RC-ELM with 2 incorporated-MLP algorithm is trained online in order to
compensation layers shows descent performance with respect detect the real and imaginary part of the received symbols.
to the classic ELM receiver as well as the RC-ELM receivers For each part, the number of neurons in each layer is 4, 8
with 3 and 4 compensation layers. For user 1, compared to and 6 respectively. Similar to the ELM receivers, the number
the classic ELM, the EVM performance improvement with of input layer and output layer is respectively chosen to be
RC-ELM with 2 compensation layers, within 25 − 30 dB equal to 2 and 4. Activation function tanh is also considered
SNR, for α = 102 , 103 , 104 and 105 are observed to be for the MLP receiver at each hidden layer and the weight
6 VOLUME 4, 2016
This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://creativecommons.org/licenses/by/4.0/
This article has been accepted for publication in IEEE Access. This is the author's version which has not been fully edited and
content may change prior to final publication. Citation information: DOI 10.1109/ACCESS.2023.3242917
TABLE 2. EVM vs SNR of the classic ELM and the RC-ELM receivers in training stage for different regularization parameters.
SNR 0 5 10 15 20 25 30 35 40
Classic ELM (α = 10−2 )
User 1 45.114 29.823 20.021 14.816 13.061 12.416 12.175 12.103 12.083
User 2 127.732 123.888 111.104 102.550 98.885 95.732 93.653 93.593 91.100
RC-ELM (2 compensation layer, α = 10−2 )
User 1 44.477 28.247 17.367 10.732 8.013 7.048 7.060 7.743 8.491
User 2 126.553 123.761 107.657 98.470 91.615 82.686 79.169 84.808 88.493
RC-ELM (3 compensation layer, α = 10−2 )
User 1 44.639 28.653 18.074 11.903 9.574 8.823 8.871 9.447 10.028
User 2 127.104 122.967 108.863 100.016 94.687 87.198 87.897 91.532 89.807
RC-ELM (4 compensation layer, α = 10−2 )
User 1 44.739 28.904 18.502 12.579 10.423 9.736 9.753 10.210 10.659
User 2 127.299 123.426 109.398 101.168 95.789 89.804 90.158 92.788 90.486
parameters are updated with the learning rate of 0.005 and algorithms (in testing stage). The ELM receivers shows better
momentum of 0.8. Fig. 6 presents the BER obtained by performance for α = 10−5 .
the MMSE, the trained classic and the RC-ELMs as well
as the MLP receivers. For all the values of α, both of the The accuracy of the channel estimation determines the
ELM receivers provide better performance than the MLP inter-user interference mitigation and as a result, the re-
receivers. For α = 10−5 , the BER performances by both covery of the signal in NOMA-based communication net-
of the ELM receivers are almost identical. Even the ELM works. Thus, any error in the channel estimation will affect
receivers show improved performance against the MMSE the overall signal recovery process by means of the linear
receiver. At the BER value of about 10−2 , about 2.5 dB and 5 receiver, since such receiver utilize the estimated channel
dB gains are observed by the ELM receivers (with respect to information. On the other hand, ELM receiver does not re-
the MMSE receiver) for user 1 and user 2 respectively. Table quire to directly estimate channel. It rather uses the reference
3 presents the EVM performance of the MMSE and the ML symbols to perform signal detection and minimize the inter-
ference. Contrary to the complicated structure of the MLP
VOLUME 4, 2016 7
This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://creativecommons.org/licenses/by/4.0/
This article has been accepted for publication in IEEE Access. This is the author's version which has not been fully edited and
content may change prior to final publication. Citation information: DOI 10.1109/ACCESS.2023.3242917
(a) (b)
(c) (d)
FIGURE 6. BER for MMSE, MLP, ELM and RC-ELM-based MIMO-NOMA receivers (in testing stage with (a) α = 10−2 (b) α = 10−3 (c) α = 10−4 (d)
α = 10−5 ).
algorithm-based approach, ELM does not require tuning of shown improved performance against the MMSE and the
input weights and biases, which simplifies its application. MLP receivers. Furthermore, it is shown that the RC-ELM
The addition of the compensation layers in ELM for RC- receiver training is more reliable than the conventional ELM
ELM receiver may increase complications. However, it is training. The automatic estimation of the RC-compensation
able to minimize the error caused in the training of the ELM’s layer count in order to enhance the performance of its
ELM algorithm, which is reflected by the BER and the EVM input-output mapping could be a future research target using
analyses in training stage. RC-ELM.
VI. CONCLUSION
REFERENCES
An RC-ELM based receiver is studied in this paper for
[1] S. R. Islam, N. Avazov, O. A. Dobre, and K.-S. Kwak, “Power-domain
designing a receiver for the MIMO-NOMA aided IoT sys- non-orthogonal multiple access (NOMA) in 5G systems: Potentials and
tem. The proposed receiver uses the classic ELM algorithm challenges,” IEEE Communications Surveys & Tutorials, vol. 19, no. 2,
for equalizing the symbols and the additional compensation pp. 721–742, 2016.
[2] B. Kimy, S. Lim, H. Kim, S. Suh, J. Kwun, S. Choi, C. Lee, S. Lee, and
layers are used to minimize the errors introduced in the D. Hong, “Non-orthogonal multiple access in a downlink multiuser beam-
classic ELM training. The BER and the EVM analyses of forming system,” in MILCOM 2013-2013 IEEE Military Communications
both of the ELM receivers in training stage is conducted. Conference. IEEE, 2013, pp. 1278–1283.
[3] J. S. Yeom, H. S. Jang, K. S. Ko, and B. C. Jung, “BER performance of up-
The performance of the RC-ELM is also compared to the
link NOMA with joint maximum-likelihood detector,” IEEE Transactions
MMSE, classic ELM and MLP receivers. In terms of BER on Vehicular Technology, vol. 68, no. 10, pp. 10 295–10 300, 2019.
and EVM, It is shown that both of the ELM receivers have [4] H. Wang, R. Zhang, R. Song, and S.-H. Leung, “A novel power min-
8 VOLUME 4, 2016
This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://creativecommons.org/licenses/by/4.0/
This article has been accepted for publication in IEEE Access. This is the author's version which has not been fully edited and
content may change prior to final publication. Citation information: DOI 10.1109/ACCESS.2023.3242917
TABLE 3. EVM performance of MMSE, MLP, classic ELM and RC-ELM receivers (in testing stage for different regularization parameters).
SNR 0 5 10 15 20 25 30 35 40
MMSE
User 1 110.562 52.055 32.148 20.966 13.71 10.67 5.382 2.711 1.595
User 2 293.536 141.744 122.59 101.899 88.089 72.782 59.499 42.971 27.917
MLP
User 1 164.653 166.454 170.906 135.689 92.724 167.884 168.269 155.838 152.643
User 2 106.954 108.428 109.209 109.37 108.12 108.907 110.219 110.849 110.053
imization precoding scheme for MIMO-NOMA uplink systems,” IEEE nications,” IEEE Transactions on Vehicular Technology, vol. 69, no. 12,
Communications Letters, vol. 22, no. 5, pp. 1106–1109, 2018. pp. 15 398–15 411, 2020.
[5] L. Liu, Y. Chi, C. Yuen, Y. L. Guan, and Y. Li, “Capacity-achieving [15] Y. S. Cho, J. Kim, W. Y. Yang, and C. G. Kang, MIMO-OFDM wireless
MIMO-NOMA: iterative LMMSE detection,” IEEE Transactions on Sig- communications with MATLAB. Singapore: John Wiley & Sons, 2010.
nal Processing, vol. 67, no. 7, pp. 1758–1773, 2019. [16] D. F. Carrera, C. Vargas-Rosales, N. M. Yungaicela-Naula, and
[6] E. N. Tominaga, O. L. López, H. Alves, R. D. Souza, and J. L. Rebelatto, L. Azpilicueta, “Comparative study of artificial neural network based
“Performance analysis of MIMO-NOMA iterative receivers for massive channel equalization methods for mmwave communications,” IEEE Ac-
connectivity,” IEEE Access, vol. 10, pp. 46 808–46 822, 2022. cess, vol. 9, pp. 41 678–41 687, 2021.
[7] J. Liu, K. Mei, X. Zhang, D. Ma, and J. Wei, “Online extreme learning [17] D. F. Carrera, C. Vargas-Rosales, L. Azpilicueta, and J. A. Galaviz-
machine-based channel estimation and equalization for OFDM systems,” Aguilar, “Comparative study of channel estimators for massive mimo 5g
IEEE Communications Letters, vol. 23, no. 7, pp. 1276–1279, 2019. nr systems,” IET Communications, vol. 14, no. 7, pp. 1175–1184, 2020.
[18] D. Gao and Q. Guo, “Extreme learning machine-based receiver for mimo
[8] M. Yao, M. Sohul, V. Marojevic, and J. H. Reed, “Artificial intelligence
led communications,” Digital Signal Processing, vol. 95, p. 102594, 2019.
defined 5G radio access networks,” IEEE Communications Magazine,
[19] J. Zhang, W. Xiao, Y. Li, and S. Zhang, “Residual compensation extreme
vol. 57, no. 3, pp. 14–20, 2019.
learning machine for regression,” Neurocomputing, vol. 311, pp. 126–136,
[9] J.-M. Kang, I.-M. Kim, and C.-J. Chun, “Deep learning-based MIMO- 2018.
NOMA with imperfect SIC decoding,” IEEE Systems Journal, vol. 14, [20] L. Noriega, “Multilayer perceptron tutorial,” School of Computing.
no. 3, pp. 3414–3417, 2019. Staffordshire University, 2005.
[10] L. Chuan, C. Qing, and L. Xianxu, “Uplink NOMA signal transmission
with convolutional neural networks approach,” Journal of Systems Engi-
neering and Electronics, vol. 31, no. 5, pp. 890–898, 2020.
[11] M. Khani, M. Alizadeh, J. Hoydis, and P. Fleming, “Adaptive neural
signal detection for massive MIMO,” IEEE Transactions on Wireless
Communications, vol. 19, no. 8, pp. 5635–5648, 2020.
[12] D. F. Carrera, D. Zabala-Blanco, C. Vargas-Rosales, and C. A. Azurdia-
Meza, “Extreme learning machine-based receiver for multi-user massive
MIMO systems,” IEEE Communications Letters, vol. 25, no. 2, pp. 484–
488, 2020.
[13] D. F. Carrera, C. Vargas-Rosales, D. Zabala-Blanco, N. M. Yungaicela-
Naula, C. A. Azurdia-Meza, M. Marey, and A. D. Firoozabadi, “Novel
multilayer extreme learning machine as a massive MIMO receiver for
millimeter wave communications,” IEEE Access, 2022.
[14] Y. Tian, G. Pan, and M.-S. Alouini, “On NOMA-based mmWave commu-
VOLUME 4, 2016 9
This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://creativecommons.org/licenses/by/4.0/
This article has been accepted for publication in IEEE Access. This is the author's version which has not been fully edited and
content may change prior to final publication. Citation information: DOI 10.1109/ACCESS.2023.3242917
10 VOLUME 4, 2016
This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://creativecommons.org/licenses/by/4.0/